Five LLMs vote on hardware inspection: X-ray CT tops the ranking
jwt0625 · x · 2026-10-12
The author had five LLMs vote to rank hardware inspection imaging techniques: X-ray CT won unanimously with 22 points, ahead of EOTPR, TDTR, FIB-SEM and optical profilometry. Drawing on experiments using Claude to drive Blender and build 3D models from images, they argue LLM reverse-engineering of software is becoming common, hardware is mostly less complex than software, and the real bottleneck for AI understanding hardware is imaging and inspection equipment — making them bullish on that space.
Related event: Claude-Driven Blender Rebuilds 3D Models From Images(2 posts)→
More from coding & agent
- Dev builds Claude-coded 'daily wearable' firmware packing 27 games and 16 utilities — ezshine · 2026-10-12
- MCP memory app keeps persistent context across Claude, ChatGPT and Codex — Jolly-Scientist-2484 · 2026-10-12
- HANDBOOK.md benchmark: top agents pass just 36.2% of 65 policy-heavy agentic tasks — bibryam · 2026-10-12
- LangChain's Harrison Chase backs the bet that AI feeds will be the form factor of 2027 — hwchase17 · 2026-10-12
- AWS open-sources Strands Decider 2B, a laptop-runnable decision model with no text generation — dl_weekly · 2026-10-12
- aiprox-mcp lets you discover, hire and pay autonomous AI agents across Lightning, Solana and x402 rails — modelcontextprotocol · 2026-10-12